About the Role

We are seeking a talented AI Engineer who is as comfortable writing production systems code as they are building LLM-driven features. The ideal candidate has strong experience across AI/ML, Generative AI, and LLMs, but is equally at home in Go (and ideally Rust) shipping reliable, deployable software - not just prompt-chaining prototypes.

Key Responsibilities

- Design, develop, and deploy AI/ML and Generative AI solutions as production systems, not demos.
- Build applications using LLMs and related frameworks, with production-grade error handling, schema validation, and observability.
- Experience building massively-parallel multi agent orchestration harnesses
- Develop and implement RAG pipelines, prompt engineering, embeddings, and vector-database integrations.
- Work with AI agents / multi-agent systems and tool-calling architectures.
- Fine-tune, evaluate, and optimize AI/ML models for performance, accuracy, and cost.
- Integrate AI solutions with existing services, APIs, and enterprise systems.
- Own the full deployment lifecycle: containerize, ship, monitor, and operate what you build.
- Translate business requirements into scalable AI solutions in collaboration with cross-functional teams.

Required Skills

- Strong programming skills in Go (required), with Python as a secondary utility language. Proficiency in Rust is considered a significant value addition.
- Proficient with Linux, Docker, and git (branching, PR workflows, code review, rebase) as daily tools, not checkbox familiarity.
- Hands-on experience with Generative AI and LLMs in a production setting.
- Working knowledge of RAG architecture, embeddings, prompt engineering, and at least one vector database (Pinecone, Chroma, FAISS, Weaviate, or similar).




- Experience with LLM APIs/models and LiteLLM orchestration (OpenAI, Anthropic/Claude, Openrouter, Hugging Face, Llama, especially self-hosted models via vLLM/Ollama).
- Solid understanding of ML/DL fundamentals, model evaluation, and responsible AI practices.
- Experience with REST APIs and service integration. RPC comprehension and low level IPC integration is a big plus.
- Robust analytical and debugging skills – comfortable navigating unfamiliar codebases.

Preferred Skills

- Rust, for systems-level tooling alongside Go.
- CI/CD pipeline authorship (GitHub Actions or equivalent) and MLOps practices.
- Cloud infrastructure experience (AWS preferred; Azure/GCP accepted); storage, cost optimization.
- Experience self-hosting and operating LLM inference at scale (vLLM GPU scheduling).
- Experience with Haystack, LangChain, LlamaIndex, or similar orchestration frameworks.
- Familiarity with NLP, computer vision, or speech-based AI applications.
- Domain experience in hardware/EDA verification (SystemRDL, UVM, register-based design) is a plus, not required.

Qualifications

- Bachelor's or master's degree in Computer Science, AI, ML, Data Science, or related field.
- Demonstrated hands-on shipping of AI/ML or GenAI systems to production – portfolio, GitHub, or open-source contributions weighed heavily.

What We Are Looking For Someone who treats "it works in a notebook" and "it works in production" as different problems, is comfortable owning a system end-to-end (model to deployment), and is excited about AI engineering as engineering - not just prompt assembly.

Location: Sector 62, Noida

Experience: 3-6 years

Employment Type: Full-time

Pay: From ₹1,500,000.00 per year

Benefits

- Health insurance
- Provident Fund

Work Location: In person

📌 AI Engineer (Noida)
🏢 Agnify Technology
📍 Noida