23 hours ago
Hyderābād, IndiaSenior
Responsibilities
- Design and develop new software features and enhancements for portfolio and managed services products.
- Maintain existing applications and resolve software defects.
- Translate business requirements into robust, performant, and scalable technical solutions.
- Build multi-agent systems involving agent roles, memory management, tool orchestration, and inter-agent communication.
- Evaluate, regression-test, and monitor LLM and agent behavior in production.
- Design prompts and NLP/NLU workflows using few-shot prompting, chain-of-thought, ReAct patterns, tool use, and function calling.
- Build, deploy, or orchestrate AI, ML, and data pipelines on Databricks.
- Fine-tune and deploy small and open-source large language models.
- Design and implement RAG pipelines, including ingestion, chunking, embeddings, and vector database integration.
- Participate in technical design discussions, code reviews, documentation, and test planning.
- Collaborate with Product Development, Analytics Engineers, and Team Leads to influence technical direction.
Requirements
- 5–8 years of hands-on software engineering industry experience.
- B.Tech or M.Tech in Computer Science or equivalent educational background.
- Experience with LLM evaluation frameworks such as DeepEval and LangSmith.
- Experience architecting and building multi-agent systems with frameworks such as LangGraph.
- Expertise in prompt engineering, NLP/NLU workflows, tool use, and function calling.
- Experience building, deploying, or orchestrating ML/AI or data pipelines on Databricks, including Data Engineering, MLflow, collaborative workflows, and jobs.
- Experience designing, fine-tuning, and deploying models such as Llama, Mistral, and OpenAI GPT.
- Strong Python proficiency and a record of building production-grade, client-facing systems.
- Strong understanding of software design patterns and database design.
- Hands-on PostgreSQL expertise, including schema design, query optimization, indexing, and relational and non-relational data models at scale.
- Practical experience with SQS, Lambda, and ECS.
- Preferred experience with service-oriented architecture, microservices, distributed systems, failure handling, large-scale data systems, rate limiting, throttling, quota management, caching, and parallel or asynchronous workflows.
- Preferred experience with RAG pipelines and vector databases such as pgvector, Weaviate, or ChromaDB.
Benefits
- Health, life, and disability insurance.
- Retirement savings plans and a discounted employee stock purchase program.
- Paid time off for 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 workplace culture.
Tech Stack
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).