3 days ago
Hyderābād, IndiaSenior
Responsibilities
- Design and develop agentic AI workflows using LangChain, LangGraph, AutoGen, CrewAI, or similar frameworks.
- Build and integrate LLM-powered applications using OpenAI, Anthropic, Meta LLaMA, Mistral, and cloud foundation models.
- Implement RAG pipelines, vector stores, semantic search, multi-agent orchestration, tool use, memory management, and reasoning loops.
- Evaluate, fine-tune, and optimize LLM behavior through prompt engineering and chain-of-thought design.
- Build scalable RESTful APIs and asynchronous microservices using Python and FastAPI.
- Design documented API contracts using OpenAPI and Swagger, and implement authentication, authorization, rate limiting, and security best practices.
- Develop event-driven and streaming architectures for real-time AI inference pipelines.
- Deploy and manage AI workloads on AWS and use Databricks for data processing, MLflow tracking, and AI/ML pipeline orchestration.
- Build CI/CD and infrastructure-as-code workflows using Terraform, AWS CDK, or similar tools.
- Write production-ready Python, conduct code reviews, mentor junior engineers, and contribute to architecture, technical roadmaps, and documentation.
Requirements
- 5–7 years of professional software engineering experience.
- Production experience with Python, including asynchronous programming, type hints, Pydantic, and dependency injection.
- Experience with GenAI technologies including LLMs, RAG, embeddings, prompt engineering, agentic frameworks, or similar systems.
- Experience building and deploying APIs with FastAPI or similar asynchronous Python frameworks.
- Experience with AWS cloud services in production environments.
- Hands-on experience with Databricks for data and AI workloads.
- Experience with SQLAlchemy, Alembic, or asynchronous ORMs, plus pytest and pytest-asyncio.
- Understanding of LLM internals, tokenization, context windows, model behavior, RAG architectures, chunking strategies, and embedding models.
- Experience with vector databases such as Pinecone, Weaviate, pgvector, ChromaDB, or FAISS.
- Experience with OpenAI API, Anthropic Claude API, AWS Bedrock, or Hugging Face models.
- Experience with AWS services including Lambda, API Gateway, ECS/EKS, S3, DynamoDB, RDS/Aurora, IAM, VPC, and Secrets Manager.
- Experience with Databricks Workflows, Delta Lake, Unity Catalog, and MLflow.
- Experience with Docker, Kubernetes, Git, CI/CD systems, distributed systems, and event streaming such as Kafka or AWS Kinesis.
- Preferred qualifications include multimodal AI experience, Azure OpenAI Service or Google Vertex AI, Terraform or Pulumi, open-source AI/ML contributions, GraphQL APIs, data engineering or MLOps experience, AWS certifications, and Databricks certification.
- A bachelor's or master's degree in Computer Science, Software Engineering, Data Science, or a related technical field is preferred, with equivalent practical experience and a demonstrable project portfolio considered.
Benefits
- Health, life, and disability insurance, retirement savings plans, a discounted employee stock purchase program, paid holidays, family leave, and company-wide wellness days.
- Flexible work accommodations supporting work/life harmony.
- Career progression planning with dedicated monthly learning and development time.
- Business Resource Groups and opportunities for volunteerism and sustainability.
- Global community and collaborative company culture.
Tech Stack
Amazon DynamoDBApache KafkaAWSDatabricksDockerFastAPIGitGitHub ActionsGitLab CI/CDGraphQLJenkinsKubernetesMLflowpytestPythonTerraform
Categories
About FactSet
FactSet builds a financial data and analytics platform used by asset managers, investment banks, hedge funds, and wealth managers for research, portfolio management, trading, and risk. Its products include the FactSet workstation, data feeds and APIs, and workflow tools like OMS/EMS, sold primarily via subscription licensing. Founded in 1978 and headquartered in Norwalk, Connecticut, FactSet is a public company listed on the NYSE (ticker: FDS).