Applied AI Engineer

We are looking for an experienced Applied AI Engineer to design and develop advanced agentic AI systems and intelligent reasoning workflows. You will work on building production-grade AI solutions capable of analyzing complex financial data, legal documents, and market information to support credit risk assessment and financial decision-making. As an early member of the engineering team, you will have the opportunity to build core AI architecture and contribute to important technical decisions.

Responsibilities:

• Design and develop stateful, multi-agent AI systems and workflows.
• Build intelligent agents capable of multi-step reasoning, planning, and decision-making.
• Work on prompt engineering and optimization using frameworks such as DSPy and GEPA.
• Implement reasoning techniques such as Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thoughts (GoT).
• Develop evaluation frameworks using LLM-as-a-Judge and scenario-based testing.
• Build RAG pipelines, memory management, and retrieval systems.
• Integrate external tools, APIs, and human-in-the-loop (HITL) workflows.
• Implement AI observability and monitoring using tools such as Langfuse, Weights & Biases, or Helicone.
• Develop ETL pipelines and work with SQL/NoSQL databases, vector databases, and graph-based data models.
• Deploy and maintain AI applications using AWS/Azure, Docker, CI/CD, and modern DevOps practices.

Requirements:

• Candidates from Tier-1 colleges.
• 5+ years of professional software development experience in Python or JavaScript.
• Hands-on experience building and deploying production-level agentic AI or complex reasoning systems.
• Strong understanding of LLMs, AI agents, LangChain, and multi-agent architectures.
• Experience with RAG, prompt engineering, memory management, and tool integration.
• Knowledge of DSPy, GEPA, and advanced reasoning techniques is highly desirable.
• Experience with LLM evaluation and observability tools such as Langfuse, W& B, or Helicone.
• Strong understanding of data engineering, ETL pipelines, SQL/NoSQL, and vector databases.
• Knowledge of Model Context Protocol (MCP) and human-in-the-loop workflows.
• Experience with AWS or Azure cloud platforms.
• Familiarity with Docker, CI/CD, and Infrastructure as Code.

Good to Have:

• Experience with RLHF or RLAIF.
• Knowledge of model fine-tuning techniques such as LoRA and QLoRA.
• Experience with graph databases and graph-based data models.
• Previous experience in fintech, financial services, credit underwriting, or risk analysis.
• Experience working with complex financial and legal documents.