Software Architect
Autodesk · Pune · 15+ yrs experience · Posted 2026-07-18
Tech stack: AWS, Azure, Google Cloud, GraphQL, Kafka
Apply on the company site · Get a referral for this role
Autodesk salary & ratings · Autodesk interview process · More live openings
About the role
Autodesk is undertaking a bold transformation to become an AI-first application platform, delivering a seamless, unified experience that fundamentally reshapes how customers and internal teams design, build, and operate within an agent-driven workspace. This platform will serve as the foundation for the next generation of Autodesk’s Design and Make software.
We are seeking a Software Architect for Agentic AI Initiatives to define, architect, and deliver advanced AI systems capable of autonomous reasoning, decision-making, and self-directed execution. This is a senior, highly influential role that blends deep technical expertise with architectural leadership and strategic vision. You will collaborate closely with engineering, product, research, and business leaders to build domain-aware intelligent systems that accelerate innovation and deliver measurable impact across the Autodesk platform.
Responsibilities:
- Architecture & Development
- Architect, design, and guide the development of AI systems, including autonomous agents, multi-agent frameworks, and LLM-powered agents.
- Define reference architectures, patterns, and best practices for integrating agentic AI into existing Autodesk platforms, services, and workflows.
- Drive architectural decisions across inference, orchestration, tool integration, memory, and feedback loops.
- Research, Prototyping & Evaluation
- Evaluate emerging AI models, frameworks, and tooling.
- Prototype, benchmark, and assess solutions for scalability, robustness, safety, cost efficiency, and performance.
- Translate research and experimentation into production-ready architectural guidance.
- Production Deployment & Operational Excellence
- Guide the deployment of agentic AI solutions into production environments with a focus on reliability, resilience, and operability.
- Define strategies for monitoring agent behavior, detecting anomalies, and refining agent policies.
- Establish feedback mechanisms for continuous learning, evaluation, and system improvement.
- Ethics, Safety & Governance
- Ensure agentic AI systems adhere to ethical principles, regulatory requirements, and Autodesk governance standards throughout their lifecycle.
- Champion best practices for data privacy, security, auditability, and responsible AI usage.
- Cross-Functional Leadership & Communication
- Partner closely with platform architects, software engineers, applied AI teams, product managers, and business stakeholders.
- Clearly communicate complex architectural concepts, trade-offs, and risks to both technical and non-technical audiences.
- Act as a technical thought leader and mentor within the organization
Qualifications:
- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field (or equivalent practical experience)
- 15+ years of professional software engineering experience, including at least 5 years in AI/ML engineering or architecture roles.
- Demonstrated experience designing and delivering complex, production-grade software systems.
- Deep understanding of AI/ML algorithms, architectures, and frameworks.
- Proven experience delivering AI-powered features or platforms in large-scale software products.
- Strong ability to work effectively across multidisciplinary, cross-functional teams.
- API and service design at scale (REST, gRPC, GraphQL), including versioning and backward compatibility.
- Distributed systems and data platforms, including microservices, service mesh, and streaming processing architectures.
- Excellent written and verbal communication skills, with the ability to explain complex technical concepts to non-technical stakeholders.
- Strong analytical and systems-thinking skills, with a track record of solving complex technical challenges.
- Ability to think strategically about the future of AI and its application to design, construction, manufacturing, and infrastructure industries.
- Experience deploying and operating AI solutions at scale on major cloud platforms (AWS, Azure, or Google Cloud Platform).
- Strong experience with
- AWS services, such as EC2, ECS, Lambda, API Gateway, S3, DynamoDB, and RDS.
- Database architecture and technologies, including relational and NoSQL systems.
- Event-driven and streaming architectures (Kafka or Kinesis), including exactly-once processing and schema evolution (Avro / Protobuf).
- Observability and SRE practices: OpenTelemetry, distributed tracing, metrics, SLIs/SLOs.
- Knowledge graphs and semantic modeling (nice-to-have): RDF/OWL, property graphs, or ML feature stores.
- Hands-on experience with RAG architectures, including embeddings, vector stores, chunking strategies, re-ranking, and retrieval evaluation.
- Experience with agent orchestration frameworks (e.g., LangGraph, Semantic Kernel), function/tool calling, and assistants-style APIs.
- AI data governance, privacy, and safety practices, including PII handling, prompt-injection defenses, content filtering, and auditability.
- LLM observability and evaluation, including offline/online evaluations, guardrails, prompt and version management, and telemetry tools (e.g., LangSmith, PromptFlow, OpenTelemetry).
- Experience deploying and operating AI solutions at scale on major cloud platforms (AWS, Azure, or Google Cloud Platform).
- Strong experience with
- AWS services, such as EC2, ECS, Lambda, API Gateway, S3, DynamoDB, and RDS.
- Database architecture and technologies, including relational and NoSQL systems.
- Event-driven and streaming architectures (Kafka or Kinesis), including exactly-once processing and schema evolution (Avro / Protobuf).
- Observability and SRE practices: OpenTelemetry, distributed tracing, metrics, SLIs/SLOs.
- Knowledge graphs and semantic modeling (nice-to-have): RDF/OWL, property graphs, or ML feature stores.
- Hands-on experience with RAG architectures, including embeddings, vector stores, chunking strategies, re-ranking, and retrieval evaluation.
- Experience with agent orchestration frameworks (e.g., LangGraph, Semantic Kernel), function/tool calling, and assistants-style APIs.
- AI data governance, privacy, and safety practices, including PII handling, prompt-injection defenses, content filtering, and auditability.
- LLM observability and evaluation, including offline/online evaluations, guardrails, prompt and version management, and telemetry tools (e.g., LangSmith, PromptFlow, OpenTelemetry).
Qualifications
- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field (or equivalent practical experience)
- 15+ years of professional software engineering experience, including at least 5 years in AI/ML engineering or architecture roles.
- Demonstrated experience designing and delivering complex, production-grade software systems.
- Deep understanding of AI/ML algorithms, architectures, and frameworks.
- Proven experience delivering AI-powered features or platforms in large-scale software products.
- Strong ability to work effectively across multidisciplinary, cross-functional teams.
- API and service design at scale (REST, gRPC, GraphQL), including versioning and backward compatibility.
- Distributed systems and data platforms, including microservices, service mesh, and streaming processing architectures.
- Excellent written and verbal communication skills, with the ability to explain complex technical concepts to non-technical stakeholders.
- Strong analytical and systems-thinking skills, with a track record of solving complex technical challenges.
- Ability to think strategically about the future of AI and its application to design, construction, manufacturing, and infrastructure industries.
- Experience deploying and operating AI solutions at scale on major cloud platforms (AWS, Azure, or Google Cloud Platform).
- Strong experience with AWS services, such as EC2, ECS, Lambda, API Gateway, S3, DynamoDB, and RDS.
- Database architecture and technologies, including relational and NoSQL systems.
- Event-driven and streaming architectures (Kafka or Kinesis), including exactly-once processing and schema evolution (Avro / Protobuf).
- Observability and SRE practices: OpenTelemetry, distributed tracing, metrics, SLIs/SLOs.
- Knowledge graphs and semantic modeling (nice-to-have): RDF/OWL, property graphs, or ML feature stores.
- Hands-on experience with RAG architectures, including embeddings, vector stores, chunking strategies, re-ranking, and retrieval evaluation.
- Experience with agent orchestration frameworks (e.g., LangGraph, Semantic Kernel), function/tool calling, and assistants-style APIs.
- AI data governance, privacy, and safety practices, including PII handling, prompt-injection defenses, content filtering, and auditability.
- LLM observability and evaluation, including offline/online evaluations, guardrails, prompt and version management, and telemetry tools (e.g., LangSmith, PromptFlow, OpenTelemetry).
Responsibilities
- Architecture & Development
- Architect, design, and guide the development of AI systems, including autonomous agents, multi-agent frameworks, and LLM-powered agents.
- Define reference architectures, patterns, and best practices for integrating agentic AI into existing Autodesk platforms, services, and workflows.
- Drive architectural decisions across inference, orchestration, tool integration, memory, and feedback loops.
- Research, Prototyping & Evaluation
- Evaluate emerging AI models, frameworks, and tooling.
- Prototype, benchmark, and assess solutions for scalability, robustness, safety, cost efficiency, and performance.
- Translate research and experimentation into production-ready architectural guidance.
- Production Deployment & Operational Excellence
- Guide the deployment of agentic AI solutions into production environments with a focus on reliability, resilience, and operability.
- Define strategies for monitoring agent behavior, detecting anomalies, and refining agent policies.
- Establish feedback mechanisms for continuous learning, evaluation, and system improvement.
- Ethics, Safety & Governance
- Ensure agentic AI systems adhere to ethical principles, regulatory requirements, and Autodesk governance standards throughout their lifecycle.
- Champion best practices for data privacy, security, auditability, and responsible AI usage.
- Cross-Functional Leadership & Communication
- Partner closely with platform architects, software engineers, applied AI teams, product managers, and business stakeholders.
- Clearly communicate complex architectural concepts, trade-offs, and risks to both technical and non-technical audiences.
- Act as a technical thought leader and mentor within the organization