Senior AI Engineer

Company Description

Zenara Technologies is a forward-thinking fintech engineering company that specializes in building intelligent, secure, and scalable technology solutions for the digital finance industry. The company focuses on developing advanced systems, AI-driven solutions, and digital platforms to enhance consumer and enterprise financial experiences. Zenara Technologies is dedicated to modernizing financial infrastructure, enabling intelligent automation, and creating future-ready solutions that ensure reliability, compliance, and innovation. Their expertise in engineering and product design is shaping the future of smarter, safer, and more intuitive financial services.

Position Overview

We are seeking an experienced Senior AI Engineer to design and implementation of sophisticated AI solutions using large language models, agentic AI frameworks, and advanced RAG systems. You will also involve in architecting scalable AI systems, mentor engineers, and drive innovation in our AI products.

Experience Level: 4-6 years (with 2+ years in AI/ML)

Employment Type: Full-time

Location: Bangalore

Key Responsibilities

1.Advanced RAG Architecture: Design and build enterprise-scale RAG pipelines with hybrid search, re-ranking, and optimization for complex knowledge bases

2.Agentic AI Leadership: Involve in architecting sophisticated multi-agent systems with LangGraph, including autonomous decision-making, tool usage, and complex workflow orchestration

3.Tool & Integration Architecture: Design of scalable tool ecosystems that integrate with agentic frameworks such as LangChain, ADK, OpenAI SDK, and MCP. Architect robust patterns for converting existing APIs and services into LLM-usable tools with proper error handling and validation

4.AI-Driven Insights & Optimization: Develop intelligent insight engines, implement advanced prompt engineering techniques, and lead model fine-tuning initiatives using LoRA and PEFT methods

5.MLOps & Production Engineering: Establish MLOps best practices including model versioning, A/B testing, monitoring, cost optimization, and scalable vector database infrastructure

6.Technical Leadership & Mentorship: Mentor junior engineers, define technical standards, evaluate new AI technologies, and collaborate cross-functionally to deliver production AI solutions

Technical Skills

Required:

Expert Python programming with strong software engineering fundamentals

Deep expertise in LangChain and LangGraph frameworks

Production experience with OpenAI, Anthropic, and Gemini APIs

Advanced knowledge of vector databases (Pinecone, Weaviate, pgvector)

Proven track record building complex RAG architectures

Strong experience with agentic AI and autonomous systems

Mastery of prompt engineering and optimization techniques

Expertise in semantic search, embeddings, and hybrid retrieval

Solid MLOps practices (CI/CD, monitoring, deployment)

Experience with model fine-tuning and evaluation methodologies

Proficiency with cloud platforms (AWS, GCP, or Azure)

Understanding of LLM limitations and mitigation strategies

Demonstrated ability to design scalable, production-ready AI systems

AI safety and responsible AI practices knowledge

Preferred Qualifications

Bachelor's/Masters degree in Computer Science, Engineering, or related field

4-6 years of software engineering with 2+ years focused on AI/ML

Demonstrated experience delivering production AI applications at scale

Track record of technical ownership and mentoring engineers

Portfolio of shipped AI products with measurable business impact

Strong system design and basic architecture capabilities

Excellent technical communication for diverse audiences

Experience with cross-functional collaboration in agile environments

Application Process

To apply, please submit:

Send your resume to highlighting AI engineering experience and impact

Portfolio or GitHub profile with production AI systems you've built

• Cover letter describing your most complex AI project and technical approach