Role Proficiency:

Independently develops error free code with high quality validation of applications guides other developers and assists Lead 1 – Software Engineering

Outcomes:

     Understand and provide input to the application/feature/component designs; developing the same in accordance with user stories/requirements.      Code debug test document and communicate product/component/features at development stages.      Select appropriate technical options for development such as reusing improving or reconfiguration of existing components.      Optimise efficiency cost and quality by identifying opportunities for automation/process improvements and agile delivery models      Mentor Developer 1 – Software Engineering and Developer 2 – Software Engineering to effectively perform in their roles      Identify the problem patterns and improve the technical design of the application/system      Proactively identify issues/defects/flaws in module/requirement implementation       Assists Lead 1 – Software Engineering on Technical design. Review activities and begin demonstrating Lead 1 capabilities in making technical decisions

Measures of Outcomes:

     Adherence to engineering process and standards (coding standards)      Adherence to schedule / timelines      Adhere to SLAs where applicable      Number of defects post delivery      Number of non-compliance issues      Reduction of reoccurrence of known defects      Quick turnaround of production bugs      Meet the defined productivity standards for project      Number of reusable components created   Completion of applicable technical/domain certifications Completion of all mandatory training requirements

Outputs Expected:

Code:

Develop code independently for the above

Configure:

Implement and monitor configuration process

Test:

Create and review unit test cases
scenarios and execution

Domain relevance:

Develop features and components with good understanding of the business problem being addressed for the client

Manage Project:

Manage module level activities

Manage Defects:

Perform defect RCA and mitigation

Estimate:

Estimate time
effort
resource dependence for one's own work and others' work
including modules

Document:

Create documentation for own work as well as perform peer review of documentation of others' work

Manage knowledge:

Consume and contribute to project related documents
share point
libraries and client universities

Status Reporting:

Report status of tasks assigned Comply with project related reporting standards/process

Release:

Execute release process

Design:

LLD for multiple components

Mentoring:

Mentor juniors on the team Set FAST goals and provide feedback to FAST goals of mentees

Skill Examples:

Explain and communicate the design / development to the customer Perform and evaluate test results against product specifications Develop user interfaces business software components and embedded software components 5 Manage and guarantee high levels of cohesion and quality6 Use data models Estimate effort and resources required for developing / debugging features / components Perform and evaluate test in the customer or target environment Team Player Good written and verbal communication abilities Proactively ask for help and offer help

Knowledge Examples:

     Appropriate software programs / modules      Technical designing      Programming languages      DBMS      Operating Systems and software platforms      Integrated development environment (IDE)      Agile methods Knowledge of customer domain and sub domain where problem is solved

Additional Comments:

Responsibilities Lead the development of fruit defect detection models using object detection and image segmentation techniques. Design and implement deep learning pipelines using frameworks like PyTorch or TensorFlow. Work closely with domain experts to define defect categories and edge cases (e.g., bruises, rot, discoloration, deformities). Build, manage, and optimize data pipelines—including dataset curation, labeling workflows, and augmentation strategies. Ensure high model performance in terms of accuracy, recall, and inference speed—across diverse lighting and background conditions. Collaborate with product and engineering teams to deploy models to production (cloud or edge-based inference). Research and apply cutting-edge computer vision techniques (e.g., YOLOv8, EfficientDet, Mask R-CNN, ViTs, or DETR). Lead and mentor junior ML engineers and researchers. Own model evaluation and explainability tools for business and QA teams. Requirements 7+ years of experience in AI/ML with a focus on computer vision and deep learning. Strong expertise in object detection and image classification techniques. Proven experience working with real-world noisy image datasets and model optimization. Proficient in Python and frameworks such as PyTorch or TensorFlow. Familiar with tools such as OpenCV, Label Studio, Roboflow, or CVAT. Solid understanding of CNNs, transfer learning, and data-centric AI practices. Experience deploying models in production environments (REST APIs, ONNX, TensorRT, etc.).