Experience: 4.00 + years
Salary: INR 6000000-10000000 / year (based on experience)
Expected Notice Period: 30 Days
Shift: (GMT+05:30) Asia/Kolkata (IST)
Opportunity Type: Office ()
Placement Type: Full Time Permanent position(Payroll and Compliance to be managed by: Stealth Start-up Dummy)
(*Note: This is a requirement for one of Uplers client - Stealth Start-up Dummy)
What do you need for this opportunity
Must have skills required:
DevOps, Python, Agentic Workflows, LLM evaluation, Llm systems, rag
Stealth Start-up Dummy is Looking for:
We are looking for an AI Generalist who lives at the intersection of research and engineering - someone who can take an LLM idea from a whiteboard sketch to a production-grade system without losing fidelity. You will design and ship agentic workflows, retrieval-augmented generation (RAG) pipelines, LLM evaluation frameworks, and model serving infrastructure that directly impact product outcomes. This is a hands-on, high-ownership role suited for an engineer who thrives in fast-moving environments and cares deeply about output quality.
WHAT YOU WILL DO :
- Design, build, and productionize LLM-powered agents and multi-step agentic workflows using frameworks such as LangChain, LangGraph, or equivalent.
- Architect and maintain RAG systems end-to-end — from document ingestion and chunking strategies to vector store selection, retrieval tuning, and re-ranking.
- Own LLM evaluation: define benchmarks, run prompt testing suites, implement LLM-as-judge and panel-of-experts evaluation frameworks, and continuously monitor model quality in production.
- Serve AI models reliably in production — selecting the right serving stack (vLLM, SGLang, Triton, or similar), optimising throughput and latency, and operating them at scale.
- Fine-tune and adapt open-source models for domain-specific tasks using techniques such as LoRA, QLoRA, and PEFT; manage the full lifecycle from data preparation to deployment.
- Build and maintain backend infrastructure to support AI systems — REST APIs, data pipelines, and integration layers using Python and FastAPI (or similar).
- Iterate rapidly on prompts, architectures, retrieval configurations, and serving setups; instrument experiments to track quality improvements with clear metrics.
- Collaborate cross-functionally with product, research, and business stakeholders to translate requirements into reliable AI solutions.
MUST-HAVE REQUIREMENTS :
- LLM Systems & Agentic Workflows: Proven, hands-on experience designing and shipping LLM-powered systems including agents, tool-use workflows, multi-step reasoning chains, and structured output pipelines. Familiarity with orchestration frameworks (LangChain, LangGraph, AutoGen, CrewAI, or similar) is expected.
- RAG Systems: Deep practical experience with retrieval-augmented generation — vector databases (Pinecone, Weaviate, Chroma, Vespa, Qdrant, or similar), chunking strategies, embedding selection, hybrid search, and retrieval ranking/re-ranking.
- LLM Evaluation: Ability to define and implement robust evaluation frameworks including benchmark construction, automated prompt testing, LLM-as-judge methodologies, and ongoing production monitoring of agents.
- AI Model Serving & Fine-Tuning: End-to-end ownership of getting models into production and keeping them there.
- Python &Backend Engineering: Strong Python skills with practical experience building APIs (FastAPI, Flask, or similar) and data pipelines. Comfort working with databases, cloud storage, and asynchronous processing.
- Experimentation Mindset: Demonstrated ability to iterate quickly — form a hypothesis, run controlled experiments, measure output quality, debug failures, and improve results systematically.
GOOD-TO-HAVE SKILLS :
- Multimodal AI: Exposure to vision-language models (VLMs), multimodal pipelines, or working with image/audio inputs alongside text.
- Real-Time Voice AI Systems: Hands-on experience building low-latency, real-time AI systems -particularly voice agents, speech-to-text pipelines, or streaming inference architectures.
- AI Observability & Eval Pipelines: Familiarity with LLM tracing tools (LangSmith, Weave, Phoenix, Arize, Prometheus/Grafana for ML), and building automated quality pipelines for continuous evaluation.
- Startup / Rapid Prototyping Experience: Comfort operating in a fast-paced, ambiguous environment-validating use cases quickly, building MVPs, and gathering early user feedback to drive iteration.
INTERVIEW PROCESS :
- L1: Tech discussion
- L2: Discussion based on prev exp + coding
- L3: Culture fit
How to apply for this opportunity
- Step 1: Click On Apply! And Register or Login on our portal.
- Step 2: Complete the Screening Form & Upload updated Resume
- Step 3: Increase your chances to get shortlisted & meet the client for the Interview!
About Uplers:
Our goal is to make hiring reliable, simple, and fast. Our role will be to help all our talents find and apply for relevant contractual onsite opportunities and progress in their career. We will support any grievances or challenges you may face during the engagement.
(Note: There are many more opportunities apart from this on the portal. Depending on the assessments you clear, you can apply for them as well).
So, if you are ready for a new challenge, a great work environment, and an opportunity to take your career to the next level, don't hesitate to apply today. We are waiting for you!
