AI/ML Engineer

Ubikon Technologies Pvt. Ltd.; Indore District; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Ubikon Technologies Pvt. Ltd. is seeking an experienced ML/AI engineer to design production-grade RAG pipelines and AI agents for enterprise clients.

You will work with leading models and ship AI products that solve real business problems. In this role, you will implement guardrails, optimize for accuracy, cost, and latency, and collaborate with clients to translate business needs into scalable AI solutions.

Qualifications

• 3+ years of ML/AI engineering experience with production deployments.
• Strong Python skills; experience with ML frameworks.
• Hands-on with orchestration frameworks like LangChain or LlamaIndex.
• Knowledge of transformer models and LLM internals.
• Experience with vector databases and embedding models.
• Strong written communication and documentation.

Responsibilities

• Design and ship production-grade RAG pipelines with vector databases (Pinecone, pgvector, Weaviate).
• Build AI agents with tool-use, multi-step reasoning, and long-term memory.
• Fine-tune and evaluate LLMs (Llama 3, Mistral, Phi) for domain-specific tasks.
• Implement guardrails: output validation, hallucination detection, prompt injection defense.
• Benchmark accuracy, cost, and latency; optimize for each.
• Collaborate with clients to translate business needs into AI systems.

Skills

Python

PyTorch

TensorFlow

LangChain

LlamaIndex

Transformer

Tools

Pinecone

pgvector

Weaviate

Job description

Join our AI team to build production LLM systems, RAG pipelines, and agentic workflows for enterprise clients. You will work with the latest models (GPT-4, Claude, Llama) and ship AI products that solve real business problems.

Responsibilities

• Design and ship production-grade RAG pipelines with vector databases (Pinecone, pgvector, Weaviate)
• Build AI agents with tool-use, multi-step reasoning, and long-term memory
• Fine-tune and evaluate LLMs (Llama 3, Mistral, Phi) for domain-specific tasks
• Implement guardrails: output validation, hallucination detection, prompt injection defense
• Benchmark accuracy, cost, and latency; optimize for each
• Collaborate with clients to translate business needs into AI systems

Requirements

• 3+ years of ML/AI engineering experience with production deployments
• Deep Python skills + one or more of PyTorch, TensorFlow, or JAX
• Hands-on with LangChain, LlamaIndex, or similar orchestration frameworks
• Strong understanding of transformer architecture, attention, and LLM internals
• Experience with vector databases and embedding models
• Strong written communication, you will document models and decisions