About Company
HCLSoftware, founded in 2019, is the software business division of HCLTech. We develop, market, and sell software products across various categories, including Business & Industry Applications, Cybersecurity, Data & Analytics, AI & Intelligent Operations, Sovereign Collaboration, Total Experience, and Specialized Software.
We drive customer success through continuous product innovation, serving over 20,000 organizations, including many Fortune 100 and Fortune 500 companies. We are also a proud partner of Scuderia Ferrari.
As a fast-growing, $2B+ software business, we have an incredible global workforce of 8,000+ employees. Join us and make an impact from Day 1this is an exciting time to be part of HCLSoftware as we expand, invest, and grow!
We take pride in our purpose-driven work ethic that is fuelled by a razor-sharp focus to make clients succeed in achieving their business outcomes. We dream, we collaborate, we experiment, and we break new ground. We are a dedicated team that looks out for each other.
We are looking for a Senior Python Developer with 4+ years of experience with strong expertise in building production-grade APIs and systems that integrate with Large Language Models (LLMs). The ideal candidate will have hands-on experience working with Anthropic Claude, Model Context Protocol (MCP), and agentic AI architectures, delivering scalable, secure, and maintainable AI-driven services.
You will play a key role in designing and implementing intelligent agents, orchestration layers, and LLM-backed APIs that power real-world applications.
Responsibilities
- Design, develop, and maintain Python-based APIs and services that integrate with LLM providers (e.g., Anthropic Claude)
- Build LLM orchestration layers supporting tool use, function calling, multi-step reasoning, and memory
- Implement and extend Model Context Protocol (MCP) servers and clients for structured LLM context exchange
- Develop agentic AI systems, including:
- Task decomposition and planning
- Tool selection and execution
- Multi-agent coordination (where applicable)
- Stateful and event-driven agent workflows
- Design scalable, modular architectures for AI-powered systems
- Ensure robust error handling, observability, logging, and monitoring for LLM-based services
- Implement secure API authentication, rate limiting, and cost-control mechanisms for LLM usage
- Optimize performance and latency for high-throughput LLM interactions
- Collaborate with product, ML, and frontend teams to translate requirements into technical solutions
- Work with our DevOps team to ensure a continuous integration and deployment of developed features happen
- Write clean, well-documented, testable code following best practices
- Contribute to design reviews, technical discussions, and architectural decisions
Skills & Qualifications
- 4+ years of experience with a start-up mentality and high willingness to learn
- Strong experience building REST and/or async APIs (e.g., FastAPI, Flask, Django)
- Hands-on experience integrating with LLM APIs, including Anthropic Claude (preferred)
- Hands-on experience in AI frameworks (e.g. PyTorch, TensorFlow, Hugging Face, LangChain, LangGraph, n8n).
- Prompt engineering and structured output handling
- Design and optimize prompts for LLMs and multimodal Gen-AI systems.
- Practical experience with agentic AI patterns, such as:
- Autonomous agents
- Tool-using agents
- Multi-step reasoning workflows
- Confidence building functional prototypes using Claude Code, Antigravity, Codex and other similar platforms
- Experience working with or implementing Model Context Protocol (MCP) integrations
- Understanding of LLM behaviors, limitations, and failure modes
- Strong knowledge of async Python (e.g., asyncio)
- Experience with databases (PostgreSQL, NoSQL, vector databases)
- Familiarity with Docker and cloud platforms (AWS, GCP, or Azure)
- CI/CD, automated testing, and production deployment experience
- Strong communication skills, team player with attention to detail who is happy working in an agile development environment
Preferred Skills
- Exposure to MLOps or AI observability tools
- Prior experience working on AI-first or AI-native products
- Ability to design guardrails, validation, and safety mechanisms around LLM outputs
