Want to know if this job is worth applying to?
Bengaluru, Karnataka, India
Onsite
About the Role
As a Lead Developer, you will own and evolve the core platform services that power our AI-driven products. You will design and build production-grade APIs, LLM-based extraction and enrichment pipelines, and agentic workflows — ensuring they are reliable, performant, and scalable.
You will work closely with AI engineers, front-end developers, and product stakeholders to translate investment use cases into robust back-end solutions.
This role is ideal for an engineer who combines deep Python expertise with hands-on experience building LLM-driven applications and who thrives in a fast-paced, product-oriented environment.
Key Responsibilities
Design, develop, and maintain back-end services and REST APIs using Python and FastAPI, serving both internal and external consumers.
Build and optimise LLM-based pipelines for information extraction, summarisation, and classification across diverse source types.
Develop and maintain agentic AI workflows using LangGraph, including tool orchestration, multi-step reasoning chains, and feedback loops.
Extend and operate the MCP server layer (FastMCP), enabling seamless integration of AI capabilities into third-party tools and workflows.
Design and maintain data models and query patterns in MongoDB Atlas, leveraging both its document database and vector store capabilities for RAG pipelines.
Build and manage data processing and scheduling pipelines using Apache Airflow, deployed on AWS EKS.
Collaborate with front-end engineers to define clean, well-documented API contracts and ensure efficient data flows.
Implement robust testing strategies (unit, integration, end-to-end) and contribute to CI/CD pipelines for reliable, automated deployments.
Participate actively in agile ceremonies, code reviews, and architectural discussions, contributing to a culture of engineering excellence.
Monitor, troubleshoot, and improve system reliability and performance across the platform.
Experience
Years of Experience: 10–17 years of professional software engineering experience, with a strong focus on Python back-end development.
LLM & AI Development: At least 1 year of hands-on experience building LLM-based applications, including one or more of: retrieval-augmented generation (RAG), agent-based systems (e.g., LangChain, LangGraph), LLM-driven data extraction, or prompt engineering.
Python Expertise: Deep proficiency in Python, including modern async frameworks (FastAPI or equivalent). Strong understanding of Python packaging, dependency management, and best practices.
Database Skills: Experience with MongoDB or similar document databases. Familiarity with vector stores and embedding-based search is highly desirable.
Cloud & Infrastructure: Practical experience with AWS services, containerisation (Docker, Kubernetes/EKS), and orchestration tools such as Apache Airflow.
API Design: Proven ability to design, build, and document RESTful APIs that are clean, versioned, and production-ready.
Software Engineering Practices: Strong grasp of version control (Git), testing frameworks (pytest, etc.), CI/CD pipelines, and agile development methodologies.
Communication: Ability to articulate technical decisions clearly to both technical and non-technical stakeholders.
Nice to Have
Experience with FastMCP or the Model Context Protocol (MCP) ecosystem.
Familiarity with LangGraph or similar agent orchestration frameworks.
Background in processing unstructured data from diverse sources (PDFs, audio, messaging platforms).
Understanding of capital markets, investment research workflows, or financial data.
Experience with observability and monitoring tools (e.g., DataDog, Prometheus, Grafana).
Degree in Computer Science, Software Engineering, or a related discipline (or equivalent practical experience).
