AI Engineer

AI Engineer Opportunity at Unico Connect, Mumbai

Unico Connect, a premier AI-native technology partner, is seeking a skilled AI Engineer to join our dynamic team in Mumbai. This hybrid role, based in Kurla (West), Mumbai, India, offers a Monday-Friday work schedule for experienced professionals with 2-4 years in the field.

As an AI Engineer, you will play a pivotal role in architecting and implementing advanced AI capabilities, agentic systems, and AI-powered platforms that are integral to our clients' live products. This position is ideal for a proactive problem-solver capable of rapidly transforming ambiguous challenges into functional prototypes and scaling them into robust, production-ready systems serving real users. You will collaborate closely with delivery pods, product managers, and clients, taking full ownership of the AI components within client engagements.

Key Responsibilities:

• Solutioning & POC Development: Translate complex customer problems into working prototypes swiftly. Select appropriate models, frameworks, and architectures to demonstrate value early and efficiently.
• LLM Application Development: Build sophisticated AI features and services leveraging LLM APIs from leading providers (OpenAI, Anthropic, Google) and open-weight models. Make informed decisions on model selection based on cost, latency, and capability trade-offs.
• Agentic System Design: Design and deploy agentic workflows using established frameworks (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or custom orchestration methods, incorporating tool use, planning, memory, and multi-step reasoning.
• API & Service Development: Develop production-ready AI services and APIs using Python and FastAPI, ensuring robust handling of streaming responses, asynchronous processing, structured outputs, and graceful degradation.
• Retrieval & Tool Integration: Implement advanced RAG pipelines with vector databases (Pinecone, Weaviate, Qdrant, pgvector, Chroma) and integrate diverse data sources through tool-calling mechanisms.
• Cost Optimization: Analyze and model the cost-effectiveness of AI features, tracking token usage, exploring prompt caching, and optimizing model routing to drive measurable improvements in unit economics.
• Production Hardening: Enhance AI solutions with comprehensive observability, tracing (LangSmith, Langfuse, OpenTelemetry), guardrails, content safety measures, and prompt injection defenses to ensure reliability under real-world traffic.
• Prompt Engineering & Evaluation: Craft, test, and iterate on prompts to achieve optimal outcomes. Develop evaluation frameworks for accuracy, hallucination, latency, and cost, conducting benchmarks to refine designs.
• Model Exploration: Stay abreast of new model releases and capabilities, conducting hands-on testing to assess performance on client-specific tasks.
• Knowledge Sharing: Continuously learn from research and industry developments, sharing insights with the team through demos and written summaries to foster collective growth.

Requirements:

• Proven Production AI Delivery (Mandatory): Demonstrated experience building and deploying at least one AI solution to production with sustained user traffic and operational ownership.
• 2-4 Years of Experience: Professional software or AI engineering background with end-to-end ownership of at least one production AI feature.
• Python & FastAPI Expertise: Strong proficiency in Python for API development, including async programming, type hints, and production-grade code.
• LLM & Agent Stack Proficiency: Hands-on experience with major LLM providers (OpenAI, Anthropic, Google) or open-weight models, and familiarity with at least one agent framework or equivalent RAG implementation.
• Rapid Solutioning: Ability to quickly prototype solutions from ambiguous problem statements.
• Cost Management Acumen: Skill in calculating, monitoring, and optimizing the costs associated with AI features.
• Startup Environment Adaptability: Self-motivated, comfortable with ambiguity, and able to thrive in a fast-paced, evolving environment.
• Continuous Learning: Up-to-date with the latest advancements in AI and model capabilities, with practical testing experience.
• Strong Communication Skills: Excellent written and verbal English for clear explanation of technical concepts to diverse audiences.

To Apply:

Interested candidates are invited to apply directly via this LinkedIn job posting or submit their resume to [HIDDEN TEXT] with the subject line 'Application – AI Engineer'. Shortlisted candidates will be contacted for the next steps in the hiring process.