GenAI Engineer

Aptech Limited; Mumbai; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

Aptech Limited is seeking a skilled AI/ML engineer to develop generative AI solutions using Python, LangChain, and HuggingFace. You will engage in prompt engineering and fine-tuning models to meet project needs, while ensuring efficient, scalable deployments in educational contexts.

Collaborate with business teams to translate requirements into technical specs, design robust architectures with FastAPI/Unicorn, and monitor performance to meet latency targets.

Qualifications

• Bachelor's degree in CS/AI or related field.
• 3-5 years of experience, with at least 1 year in AI/ML.

Responsibilities

• Generative AI solution development using Python, LangChain and HuggingFace.
• Engage in prompt engineering to create tailored AI-driven solutions.
• Fine-tune models from HuggingFace to meet project needs.
• Optimize AI models for efficiency, accuracy, and scalability in education.
• Collaborate with business teams to align AI with goals.
• Design robust architectures using FastAPI and Unicorn.
• Monitor model performance and reduce latency for real-time inference.
• Provide comprehensive documentation for models and data pipelines.

Skills

Prompt Engineering

Python Programming

AI and ML Frameworks

Deep Learning Architectures

Mathematical and Statistical Knowledge

System Architecture Design

Model Fine-Tuning

Collaboration and Communication

Continuous Learning

Education

Bachelor's degree in Computer Science, AI, or related fields

Tools

LangChain

HuggingFace

Cohere

Keras

TensorFlow

PyTorch

FastAPI

Unicorn

Job description

Brief Job Description

1. Generative AI Solution Development:
   • Develop and implement advanced solutions using Generative AI technologies, leveraging frameworks such as Python, LangChain, and HuggingFace.
   • Engage in prompt engineering, working with Large Language Models (LLMs) to create tailored AI-driven solutions.
   • Ensure response accuracy of prompts. Make sure the prompts generate desired outcomes and adhere to instructions.
2. Model Fine-Tuning and Optimization:
   • Fine-tune pre-trained models from HuggingFace and other platforms to meet project-specific requirements.
   • Optimize AI models for efficiency, accuracy, and scalability in educational contexts.
   • Achieve minimum accuracy thresholds for models.
   • Reduce model training time and computational resource usage.
   • Innovate AI techniques or algorithms at least once per quarter.
3. Collaboration with Business Teams:
   • Collaborate with business stakeholders to align AI solutions with organizational goals, translating business requirements into technical specifications.
   • Participate in cross-functional collaboration meetings, ensuring effective communication of AI model capabilities.
4. AI Frameworks and Tooling:
   • Utilize frameworks like LangChain, Cohere, Keras, TensorFlow, and PyTorch for developing, testing, and deploying AI models.
   • Integrate AI solutions into existing systems for seamless user experiences.
   • Ensure AI deployment times are within defined timelines (e.g., from training to production).
   • Maintain model latency below a defined threshold for real-time inference (e.g., under decided milliseconds).
5. Research and Innovation:
   • Stay updated on the latest advancements in Generative AI, machine learning, and deep learning technologies.
   • Experiment with new methodologies and emerging AI technologies to innovate and enhance existing solutions.
   • Introduce innovative AI algorithms or approaches at least once per quarter.
6. System Architecture and Integration:
   • Design robust system architectures using frameworks like FastAPI and Unicorn to support AI-driven applications.
   • Ensure AI solutions are scalable, maintainable, and integrated effectively with other system components.
   • Ensure efficient use of computing resources and optimize costs while maintaining performance standards.
7. Performance Monitoring and Improvement:
   • Monitor AI model performance, applying ML engineering metrics to continuously improve outcomes.
   • Troubleshoot issues related to model performance and integration, resolving critical bugs quickly.
   • Reductions in code execution time and model bugs.
   • Ensure AI-related code has unit testing coverage for robustness.
8. Documentation:
   • Provide comprehensive documentation for all developed models, data pipelines, and processes, explaining functionality and edge cases.
   • Maintain detailed documentation of new features and code implementations.
   • Ensure step-by-step deployment and retraining documentation, with minimal user-reported gaps or confusion.

• Education: Bachelor''s degree or equivalent experience in Computer Science, AI, or related fields.
• Experience: 3-5 years of experience, with at least 1 year specializing in AI/ML.

• Prompt Engineering
• Python Programming
• AI and ML Frameworks
• Deep Learning Architectures
• Mathematical and Statistical Knowledge
• System Architecture Design
• Model Fine-Tuning
• Collaboration and Communication
• Continuous Learning