AI solution Engineer

Wissen Technology is Hiring forAI solution Engineer

About Wissen Technology:

At Wissen Technology, we deliver niche, custom-built products that solve complex business challenges across industries worldwide. Founded in 2015, our core philosophy is built around a strong product engineering mindset—ensuring every solution is architected and delivered right the first time. Today, Wissen Technology has a global footprint with 2000+ employees across offices in the US, UK, UAE, India, and Australia. Our commitment to excellence translates into delivering 2X impact compared to traditional service providers. How do we achieve this Through a combination of deep domain knowledge, cutting-edge technology expertise, and a relentless focus on quality. We don't just meet expectations—we exceed them by ensuring faster time-to-market, reduced rework, and greater alignment with client objectives. We have a proven track record of building mission-critical systems across industries, including financial services, healthcare, retail, manufacturing, and more. Wissen stands apart through its unique delivery models. Our outcome-based projects ensure predictable costs and timelines, while our agile pods provide clients with the flexibility to adapt to their evolving business needs. Wissen leverages its thought leadership and technology prowess to drive superior business outcomes. Our success is powered by top-tier talent. Our mission is clear: to be the partner of choice for building world-class custom products that deliver exceptional impact—the first time, every time.

Job Summary: We are seeking a highly skilled Applied AI Engineer with 4–10 years of software engineering experience and 1–3+ years of hands‑on applied AI development. This role focuses on building AI‑powered solutions including RAG pipelines, LLM‑based agents, automation workflows, and production-grade AI systems for a major global bank's enterprise transformation program.
This is a hands-on builder role—ideal for engineers who have shipped real AI systems, worked with LLM APIs, and built retrieval/agentic workflows using modern AI tooling

Experience: 4- 10 years

Location:Bangalore

Mode of Work:Full time

KeyResponsibilities:

• Design, build, and deploy RAG (Retrieval‑Augmented Generation) pipelines using modern retrieval frameworks and vector databases.
  
• Build LLM‑powered applications using APIs such as Claude / Anthropic or equivalent LLM stacks.
  
• Develop AI workflows using LangChain or similar orchestration frameworks for chaining, tool use, and multi-step reasoning.
  
• Build AI agents and workflow automation systems capable of autonomous, multi‑step task execution.
  
• Implement vector storage, embedding pipelines, indexing strategies, and retrieval architectures.
  
• Work with business stakeholders to translate ambiguous requirements into actionable AI engineering solutions.
  
• Implement governance components—logging, monitoring, cost controls, and safe‑execution patterns.
  
• Collaborate with cross‑functional teams (engineering, product, data, and business teams).
  
• Contribute to architecture discussions, design reviews, and technical decision‑making.
  
• Ship production-ready AI systems with strong testing, observability, and reliability.
  
  

• Hands-on RAG development including retrieval systems, chunking, indexing, evaluation, and pipeline orchestration.
  
  
• Experience with NotebookLM, RAG tooling, notebooklm‑py, or similar retrieval libraries.
  
• Strong experience with Claude / Anthropic APIs, Claude Code, or equivalent LLM provider APIs.
  
• Proficiency with vector databases: Pinecone, Chroma, Weaviate, or similar.
  
• Strong understanding of embedding-based retrieval, indexing strategies, and vector search.
  
• Practical experience with LangChain or other AI orchestration frameworks.
  
• Experience building AI agents/workflows beyond simple chatbots.
  
• Strong Python development skills—Python‑first tooling.
  
• Demonstrated experience shipping production-grade AI systems.
  
• Ability to work directly with non‑technical stakeholders and explain technical concepts clearly.
  
• 4–10 years in software engineering with 1–3+ years focused on applied AI.
  
  

Good To Have Skills:

• Awareness of LLM governance, monitoring, cost control, and responsible AI practices.
  
  
• Strong GitHub portfolio with published AI projects (highly valued by the client; can offset lack of advanced degrees).
  
• Experience with financial services is a plus, but not mandatory.
  
• Knowledge of real-world AI evaluation, benchmarking, and observability.
  
• Understanding of retrieval metrics, vector optimization, and agent evaluation frameworks.
  
• Exposure to multi‑tenant AI systems, enterprise-grade AI workflows, or secure AI deployments.
  
  

Wissen Sites:

Website: www.wissen.com

LinkedIn: https://www.linkedin.com/company/wissen-technology

Wissen Leadership: https://www.wissen.com/company/leadership-team/

Wissen Live: