Bachelor's or Master's degree in Computer Science, AI, or a related field.
3–7 years of experience in AI/ML engineering, preferably with LLMs or AI agents in production.
Strong programming skills in Python with experience in ML frameworks such as PyTorch or TensorFlow.
Hands-on experience with LLMs, embeddings, RAG pipelines, and vector databases (Pinecone, Weaviate, etc.), plus familiarity with MLOps, CI/CD pipelines, and cloud deployment (AWS, GCP, or Azure).
Requirements:
Build and maintain AI agent systems (LLM-based) with a focus on reliability and factual accuracy.
Implement and optimize hallucination detection models (e.g., HHEM) in production pipelines.
Develop RAG pipelines: semantic search, vector databases, and data retrieval to ground AI responses in real data.
Apply Responsible AI practices: guardrails, transparency, logging, and human-in-the-loop escalation.
Job description
Requirements:
Bachelor's or Master's degree in Computer Science, AI, or related field.
3–7 years of experience in AI/ML engineering, preferably with LLMs or AI agents in production.
Strong programming skills in Python, with experience in ML frameworks such as PyTorch or TensorFlow.
Hands-on experience with LLMs, embeddings, RAG pipelines, and vector databases (Pinecone, Weaviate, etc.).
Familiarity with MLOps, CI/CD pipelines, and cloud deployment (AWS, GCP, or Azure).
Experience with Responsible AI, bias mitigation, or hallucination detection is a plus.
Strong problem-solving skills and ability to work in a fast-paced, collaborative environment.
Excellent communication skills to explain technical concepts to non-technical stakeholders.
Experience with AI agent frameworks such as LangChain, AutoGPT, or LlamaIndex.
Prior work in regulated or high-stakes industries (healthcare, finance, legal).
Open-source contributions or research publications in AI/ML.
Product-oriented mindset with experience in translating business requirements into technical solutions.
Responsibilities:
Build and maintain AI agent systems (LLM-based) with a focus on reliability and factual accuracy.
Implement and optimize hallucination detection models (e.g., HHEM) in production pipelines.
Develop RAG pipelines: semantic search, vector databases, and data retrieval to ground AI responses in real data.
Apply Responsible AI practices: guardrails, transparency, logging, and human-in-the-loop escalation.
Optimize system performance for latency, scalability, and cost-efficiency.
Collaborate with cross-functional teams (product, UX, data, customers) to deliver features.
Mentor junior engineers and support knowledge sharing within the team.
Contribute to internal tools, open-source projects, or research publications when relevant.
