Senior Software Engineer AI LLM

Job Title: Senior Software Engineer – AI / LLM (SSE)

Location: On-Site

Department: Engineering

Employment Type: Full-Time

About the Role

We are seeking an experienced Senior Software Engineer – AI / LLM to design, architect, and deploy production-grade Large Language Model (LLM) systems and agentic workflows. In this on-site role, you will bridge modern generative AI research and robust backend software engineering, building low-latency, scalable pipelines, fine-tuning state-of-the-art models, and integrating advanced retrieval systems directly into our core product architecture.

Key Responsibilities

• Architecture & Development: Design, build, and maintain production-ready backend architectures powered by proprietary and open-weight LLMs (e.g., Llama, Mistral, GPT, Claude).
• RAG & Context Management: Architect high-throughput Retrieval-Augmented Generation (RAG) pipelines, semantic search layers, and caching strategies using vector databases.
• Agentic Workflows & Tooling: Implement autonomous, multi-agent frameworks, function-calling workflows, and evaluation harnesses to orchestrate complex reasoning tasks.
• Fine-Tuning & Model Optimization: Fine-tune models (LoRA, QLoRA, full fine-tuning) for domain-specific tasks and optimize inference using quantization (GGUF, AWQ, TensorRT-LLM, vLLM).
• LLMOps & Monitoring: Establish end-to-end evaluation, observability, prompt versioning, and guardrail frameworks (evaluating latency, cost, drift, toxicity, and hallucination rates).
• Collaboration & Mentorship: Work alongside product, infrastructure, and domain engineering teams on-site; conduct code reviews, define best practices, and mentor junior engineers.

Qualifications & Experience

• Experience: 5+ years of overall software engineering experience, with at least 2+ years dedicated to building and deploying machine learning/LLM applications in production.
• Programming: Advanced proficiency in Python; solid experience with languages like Go, Rust, or C++ is a strong plus.
• LLM Tooling & Frameworks: Deep practical experience with frameworks such as LangChain, LlamaIndex, LiteLLM, vLLM, Hugging Face Transformers, and evaluation suites (e.g., Ragas, TruLens).
• Data & Vector Infrastructure: Hands-on expertise with vector search engines (e.g., Pinecone, Qdrant, Milvus, pgvector, Weaviate) alongside relational/NoSQL databases.
• Inference & Deployment: Practical understanding of model serving engines (Triton, vLLM, Ollama), containerization (Docker, Kubernetes), and cloud infrastructure (AWS/GCP/Azure).
• Education: Bachelor’s or Master’s degree in Computer Science, Data Science, Artificial Intelligence, or equivalent industry experience.

Preferred Skills

• Experience deploying models on private/on-prem GPU clusters or specialized hardware accelerators.
• Familiarity with synthetic data generation pipelines, reinforcement learning from human/AI feedback (RLHF/RLAIF), and automated testing suites for non-deterministic systems.
• Background in data security, PII redaction, and compliance when integrating enterprise LLMs.

Pay: ₹675,878.14 - ₹1,678,312.65 per year

Benefits:

• Paid sick time

Work Location: In person