Back to All Open Roles
Custom AI & LLM Systems Engineer
Design and deploy production-grade agentic workflows, enterprise hybrid RAG pipelines, low-latency streaming endpoints, and automated prompt evals using Python, LangChain, and vector stores.
WHAT YOU WILL OWN
Key Responsibilities
- Build production-ready Agentic AI systems with autonomous tool calling, self-correction, and structured outputs.
- Engineer low-latency hybrid RAG pipelines combining dense embeddings (pgvector/Pinecone) with sparse keyword retrieval.
- Develop streaming inference endpoints with FastAPI, WebSockets, and PII masking for enterprise privacy compliance.
- Benchmark model evaluations (Ragas / LangSmith), conduct regression testing, and fine-tune open-weight models.
- Integrate frontier LLMs (Claude 3.5, OpenAI, DeepSeek, Llama 3) into enterprise SaaS backbones.
- Write automated evaluation scripts to detect hallucination, measure retrieval recall, and optimize latency.
WHAT YOU BRING
Skills & Qualifications
- 3+ years of production software engineering with 2+ years dedicated to AI/ML or LLM engineering.
- Strong mastery of Python, async programming, FastAPI, LangChain / LlamaIndex, and vector databases.
- Practical experience with embedding models, token optimization, prompt caching, and context management.
- Strong foundation in distributed systems, API security, and containerized deployment on cloud infrastructure.
- Continuous passion for following frontier AI research and translating experimental papers into real systems.
PRIMARY TECH STACK & DOMAINS
#Python#LangChain#LlamaIndex#pgvector / Pinecone#FastAPI#Prompt Evals#Claude 3.5 & OpenAI#RAG Architecture
BENEFITS & CULTURE
Why Join Our Senior Bench
100% Remote or Hybrid options with flexible hours
Uncapped budget for AI compute, APIs, and model experimentation
Direct mentorship from senior AI Solution Architects
5-Day Work Week with focus on deep technical flow
Top-tier compensation and paid frontier tech courses
APPLY FOR THIS ROLE
Submit Your Profile
Join our senior bench. We evaluate candidates based on code quality and pragmatic problem solving.
Or send your resume directly to our recruitment desk:
[email protected]Explore Other Active Roles
View all rolesMobile Engineering Division
Senior Flutter & Mobile Engineer
Looking for a seasoned Flutter engineer with deep expertise in Dart, state management (Riverpod), 60/120 FPS render loops, offline-first SQLite database synchronization, and native Android/iOS bridging.
Ahmedabad HQ / Hybrid / RemoteView Role
Web & Enterprise Division
Senior Laravel & Next.js Full-Stack Engineer
Join our enterprise web squad building high-traffic SaaS backends with Laravel 11/12, PHP 8+, PostgreSQL, REST/GraphQL gateways, and modern Next.js/React frontends handling high transaction volumes.
Ahmedabad HQ / RemoteView Role