Software Engineer (Context Graph, AI/ML)
Autodesk · Pune · 2–4 yrs experience · Posted 2026-07-24
Tech stack: AWS, Elasticsearch, Python
Apply on the company site · Get a referral for this role
Autodesk salary & ratings · Autodesk interview process · More live openings
About the role
We are looking for an AI/ML Software Engineer for the Search & Context Graph (CG) Platform within Autodesk Platform Services. In this role, you will help build intelligent AI systems that power search experiences and Context Graph capabilities across Autodesk's Industry Clouds – Fusion, Forma and Flow. You will focus on model evaluation, inferencing infrastructure, and AI automation to advance the intelligence of our platform.
Roles and Responsibilities
Build and maintain ML model evaluation frameworks to assess quality, relevance, and performance of AI models used in search and Context Graph systems
Develop and operate model inferencing pipelines to serve AI/ML models at scale with low latency and high reliability
Implement AI automation workflows to accelerate development, testing, and deployment of ML-powered features
Collaborate with Search and Context Graph engineering teams to integrate AI/ML capabilities into scalable, distributed microservices
Contribute to vector embedding pipelines and semantic search features that enhance relevance and user experience
Partner with Sr. Engineers, Leads, and Engineering Managers to design and implement AI/ML technical solutions
Work with SREs to meet SLAs of AI-powered services with monitoring, troubleshooting and optimizations
Participate in on-call rotation and help in detection and recovery of production incidents
Responsibilities:
- Build and maintain ML model evaluation frameworks to assess quality, relevance, and performance of AI models used in search and Context Graph systems
- Develop and operate model inferencing pipelines to serve AI/ML models at scale with low latency and high reliability
- Implement AI automation workflows to accelerate development, testing, and deployment of ML-powered features
- Collaborate with Search and Context Graph engineering teams to integrate AI/ML capabilities into scalable, distributed microservices
- Contribute to vector embedding pipelines and semantic search features that enhance relevance and user experience
- Partner with Sr. Engineers, Leads, and Engineering Managers to design and implement AI/ML technical solutions
- Work with SREs to meet SLAs of AI-powered services with monitoring, troubleshooting and optimizations
- Participate in on-call rotation and help in detection and recovery of production incidents
Qualifications:
- or MS in Computer Science, Machine Learning, or related field
- 2-4 years of experience building and running ML systems or AI-powered applications
- Strong machine learning fundamentals: model training, evaluation, inference, and deployment
- Proficiency in Python for ML engineering and data pipelines
- Experience with LLM APIs, prompt engineering, and working with foundation models
- Hands-on experience with vector databases (e.g. Pinecone, Weaviate, pgvector) or embedding-based retrieval systems
- Experience with Cloud infrastructure platforms such as AWS (e.g. SageMaker, Lambda,
- Familiarity with ML frameworks such as PyTorch, TensorFlow, or Hugging Face Transformers
- Experience building RAG (Retrieval Augmented Generation) architectures
- Exposure to Context Graph technologies and graph databases (e.g. Neo4j, Neptune)
- Experience with Information Retrieval and hands-on knowledge of Lucene/ElasticSearch/OpenSearch
- Familiarity with MLOps tools and pipelines (e.g. MLflow, Kubeflow, SageMaker Pipelines)
- Familiarity with AI evaluation frameworks (e.g.
- , LangSmith, HELM)
- Experience in monitoring and improving reliability of AI/ML systems at scale
- Aware of Security and Compliance challenges in Cloud AI products and platforms
- Strong communicator. You enjoy synthesizing, simplifying, and articulating complex AI/ML problems to others
- A team-player, with a result-focused passion to deliver intelligent solutions that improve user experiences
- You embrace perpetual learning in the rapidly evolving AI/ML landscape and are always ready for a new challenge
- Experience building RAG (Retrieval Augmented Generation) architectures
- Exposure to Context Graph technologies and graph databases (e.g. Neo4j, Neptune)
- Experience with Information Retrieval and hands-on knowledge of Lucene/ElasticSearch/OpenSearch
- Familiarity with MLOps tools and pipelines (e.g. MLflow, Kubeflow, SageMaker Pipelines)
- Familiarity with AI evaluation frameworks (e.g.
- , LangSmith, HELM)
- Experience in monitoring and improving reliability of AI/ML systems at scale
- Aware of Security and Compliance challenges in Cloud AI products and platforms
- Strong communicator. You enjoy synthesizing, simplifying, and articulating complex AI/ML problems to others
- A team-player, with a result-focused passion to deliver intelligent solutions that improve user experiences
- You embrace perpetual learning in the rapidly evolving AI/ML landscape and are always ready for a new challenge
- Strong communicator. You enjoy synthesizing, simplifying, and articulating complex AI/ML problems to others
- A team-player, with a result-focused passion to deliver intelligent solutions that improve user experiences
- You embrace perpetual learning in the rapidly evolving AI/ML landscape and are always ready for a new challenge
Qualifications
- or MS in Computer Science, Machine Learning, or related field
- 2-4 years of experience building and running ML systems or AI-powered applications
- Strong machine learning fundamentals: model training, evaluation, inference, and deployment
- Proficiency in Python for ML engineering and data pipelines
- Experience with LLM APIs, prompt engineering, and working with foundation models
- Hands-on experience with vector databases (e.g. Pinecone, Weaviate, pgvector) or embedding-based retrieval systems
- Experience with Cloud infrastructure platforms such as AWS (e.g. SageMaker, Lambda Familiarity with ML frameworks such as PyTorch, TensorFlow, or Hugging Face Transformers Experience building RAG (Retrieval Augmented Generation) architectures Exposure to Context Graph technologies and graph databases (e.g. Neo4j, Neptune)
- Experience with Information Retrieval and hands-on knowledge of Lucene/ElasticSearch/OpenSearch
- Familiarity with MLOps tools and pipelines (e.g. MLflow, Kubeflow, SageMaker Pipelines)
- Familiarity with AI evaluation frameworks (e.g. LangSmith, HELM)
- Experience in monitoring and improving reliability of AI/ML systems at scale
- Aware of Security and Compliance challenges in Cloud AI products and platforms Strong communicator.
- You enjoy synthesizing, simplifying, and articulating complex AI/ML problems to others
- A team-player, with a result-focused passion to deliver intelligent solutions that improve user experiences
- You embrace perpetual learning in the rapidly evolving AI/ML landscape and are always ready for a new challenge
- Experience building RAG (Retrieval Augmented Generation) architectures
- Exposure to Context Graph technologies and graph databases (e.g. Neo4j, Neptune)
- You embrace perpetual learning in the rapidly evolving AI/ML landscape and are always ready for a new challenge Strong communicator.
Responsibilities
- Build and maintain ML model evaluation frameworks to assess quality, relevance, and performance of AI models used in search and Context Graph systems
- Develop and operate model inferencing pipelines to serve AI/ML models at scale with low latency and high reliability
- Implement AI automation workflows to accelerate development, testing, and deployment of ML-powered features
- Collaborate with Search and Context Graph engineering teams to integrate AI/ML capabilities into scalable, distributed microservices
- Contribute to vector embedding pipelines and semantic search features that enhance relevance and user experience
- Partner with Sr.
- Engineers, Leads, and Engineering Managers to design and implement AI/ML technical solutions
- Work with SREs to meet SLAs of AI-powered services with monitoring, troubleshooting and optimizations
- Participate in on-call rotation and help in detection and recovery of production incidents