We're seeking a talented AI Engineer to join our team and play a key role in integrating existing LLM APIs and deploying open-source LLMs into our applications. You'll be responsible for understanding LLM functionalities, crafting effective prompts, and seamlessly integrating these powerful models into our workflows, potentially leveraging frameworks like LangChain for advanced capabilities.
What you will do:
Evaluate and select appropriate LLM APIs or open-source LLMs based on project requirements
Develop a deep understanding of the chosen LLM's capabilities and limitations
Craft effective prompts to achieve desired outcomes from the LLM (e.g., text generation, translation, question answering)
Design and implement efficient pipelines for integrating the LLM with our existing infrastructure, potentially leveraging LangChain for complex workflows
Analyze and interpret LLM outputs, ensuring accuracy and relevance
Monitor and maintain the integrated LLM solution, identifying and addressing potential issues
Collaborate with data scientists, software engineers, and product managers to bring LLM-powered solutions to life
Stay up-to-date on the latest advancements in LLM technology and best practices for prompting
What makes you a great fit
2-5 years of experience in working with AI models, (at least 1 year of experience in working with LLMs)
Strong understanding of LLM architecture and functionalities (e.g., transformers, attention mechanisms)
Expertise in crafting effective prompts to achieve specific goals from an LLM
Proficiency in programming languages like Python and experience with API integration tools
Experience with frameworks like LangChain
Excellent problem-solving, analytical, and communication skills
Ability to work effectively in a cross-functional team environment
Bonus Points:
Experience in deploying and managing cloud-based AI solutions
Experience with specific LLM APIs or open-source LLMs relevant to the company's needs
Skills Required
- 2-5 years of experience working with AI models
- At least 1 year of experience working with large language models
- Strong understanding of LLM architecture and functionalities, including transformers and attention mechanisms
- Expertise crafting effective prompts for specific LLM outcomes
- Proficiency in Python
- Experience with API integration tools
- Experience with LangChain or similar frameworks
- Excellent problem-solving, analytical, and communication skills
- Ability to work effectively in a cross-functional team environment
- Experience deploying and managing cloud-based AI solutions
- Experience with relevant specific LLM APIs or open-source LLMs
What We Do
A premier global early-stage AI-first product development hub. KeyValue is the best delivery engine for product development in the Indian subcontinent – leveraging AI to deliver high-value software products and solutions across industries, geographies, and technologies. We are a 400+ engineering team that has delivered 120+ products for 80+ Companies in the last 8 years. KeyValue is proud that 40+ of these companies has raised Series A and around 15 has raised Series B or higher. KeyValue is a trusted product engineering partner for Start Ups & Scale Ups - We have ideated, conceived, strategized and built some of the globe’s most innovative Fintech & Financial Services, Digital Commerce, Adtech, Edtech, Socialtech, Logistics, Blockchain & Crypto, and Healthcare companies, helping them conceive, build and scale their products. Our inclusive culture is engaging & experiential, creating an environment to learn & collaborate with freedom to think, create, explore, grow and thrive. An ownership mindset with growth orientation forms the bedrock of exceptional client success! KeyValue delivers to customers across the globe from our Product center of excellences in Kochi & Trivandrum (India).
